Streaming Video Generation with Streaming Force Control

Hugging Face Daily Papers Papers

Summary

StreamForce is a causal, unified video generation model that provides real-time, physically grounded responses to time-varying forces through a distillation pipeline and autoregressive architecture, achieving state-of-the-art performance in force adherence and motion realism.

We introduce StreamForce, a streaming video generation framework that enables physically grounded control through continuous force inputs. Unlike prior video models that train separate models for different force types, assume fixed forces, or rely on non-causal processing, StreamForce is a causal and unified model that responds instantly and coherently to both local and global, time-varying forces. To achieve this, we design a unified force representation as a control signal and develop a distillation pipeline for force-controllable video generation. Our model combines autoregressive efficiency with force responsiveness, sustaining stable photometric and dynamic realism. StreamForce runs at up to 16.6 FPS on a single GPU, achieving state-of-the-art performance in both force adherence and motion realism. Project website: https://neu-vi.github.io/StreamForce/
Original Article
View Cached Full Text

Cached at: 06/08/26, 07:14 AM

Paper page - Streaming Video Generation with Streaming Force Control

Source: https://huggingface.co/papers/2606.07508

Abstract

StreamForce is a causal, unified video generation model that provides real-time, physically grounded responses to time-varying forces through a distillation pipeline and autoregressive architecture.

We introduce StreamForce, astreaming video generationframework that enables physically grounded control through continuous force inputs. Unlike prior video models that train separate models for different force types, assume fixed forces, or rely on non-causal processing, StreamForce is a causal and unified model that responds instantly and coherently to both local and global, time-varying forces. To achieve this, we design a unified force representation as a control signal and develop adistillation pipelineforforce-controllable video generation. Our model combinesautoregressive efficiencywith force responsiveness, sustaining stable photometric and dynamic realism. StreamForce runs at up to 16.6 FPS on a single GPU, achieving state-of-the-art performance in both force adherence and motion realism. Project website: https://neu-vi.github.io/StreamForce/

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2606\.07508

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.07508 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.07508 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.07508 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Stream-T1: Test-Time Scaling for Streaming Video Generation

Hugging Face Daily Papers

Stream-T1 is a proposed framework for test-time scaling in streaming video generation, improving temporal consistency and quality through mechanisms like noise propagation and reward pruning. The paper addresses the high computational costs of existing diffusion-based methods by leveraging chunk-level synthesis.